Triple

T17570020
Position Surface form Disambiguated ID Type / Status
Subject Gevgelija E427910 entity
Predicate locatedOn P40 FINISHED
Object E75 European route NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: E75 European route | Statement: [Gevgelija, locatedOn, E75 European route]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: E75 European route
Context triple: [Gevgelija, locatedOn, E75 European route]
  • A. European route E75 chosen
    European route E75 is a major north–south European highway running from northern Norway through several Central and Eastern European countries to Greece.
  • B. E372 European route
    The E372 European route is an international road that forms part of the trans-European E-road network, connecting major cities between Poland and Ukraine.
  • C. E15 European route
    E15 European route is a major north–south trans-European highway running from Inverness in Scotland through England and France to Algeciras in southern Spain.
  • D. E20 European route
    E20 European route is a major trans-European highway running from Ireland through the United Kingdom and Scandinavia to Russia, forming part of the international E-road network.
  • E. E29 European route
    The E29 European route is an international road in Western Europe that connects major cities across Luxembourg and Germany as part of the trans-European E-road network.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592fe8408190bd8fed1920ab3601 completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.